The present invention concerns a device for managing voice data. The embodiment described comprises apparatus for displaying a visual representation of a voice message and processor circuitry for associating markers with segments of the message. The markers are indicative of particular storage areas, e.g. a telephone number storage area, a calendar storage area etc. Association of a marker with a segment of a voice message automatically causes that segment to be linked with the corresponding storage area so that the segment can later be retrieved in the context of a user interface for that particular storage area.

Patent
   5742736
Priority
Apr 22 1994
Filed
Apr 19 1995
Issued
Apr 21 1998
Expiry
Apr 21 2015
Assg.orig
Entity
Large
192
4
all paid
1. A device for storing speech input comprising:
means for specifying a marker having a particular connotation;
means for associating the marker with all or part of the speech input;
means for automatically linking the speech input associated with the marker to a storage area such that information enabling retrieval of the speech input associated with the marker is stored in the storage area; and
an application corresponding to the connotation of the marker which, upon execution, provides access through a user interface to the speech input associated with the marker from the information stored in said storage area in accordance with said means for automatically linking.
2. A device according to claim 1 wherein the means for specifying a marker comprises means for selecting a marker from a set of markers.
3. A device according to claim 2 wherein the set of markers comprises iconic representations of the corresponding storage areas.
4. A device according to claim 1 comprising means for displaying a representation of the speech input.
5. A device according to claim 4 comprising means for automatically segmenting the speech input.
6. A device according to claim 5 comprising means for automatically segmenting the speech input into silent and non-silent parts.
7. A device according to claim 1, further comprising means for associating a marker with a part of the speech input by time synchronization.
8. A device according to claim 1, further comprising means for associating a marker with a part of the speech input by user input.
9. A device according to claim 8 comprising means for associating a marker with a part of the speech input by manipulation of an input device.
10. A device according to claim 9 comprising means for associating a marker with a part of the speech input by spoken commands.
11. A device according to claim 1 wherein the linking means comprises means for copying the speech input associated with the marker to the corresponding storage area.
12. A device according to claim 1, wherein the linking means comprises means for moving the speech input associated with the marker to the corresponding storage area.
13. A device according to claim 1 wherein the linking means comprises means for providing a pointer to the speech input associated with the marker in the corresponding storage area.
14. A device according to claim 1 wherein the linking means comprises means for providing an index into the original voice data containing the speech input associated with the marker.
15. A device according to claim 1, wherein the device comprises a plurality of applications, each corresponding to one of a plurality of marker connotations.
16. A device according to claim 15, wherein the device comprises a plurality of storage areas for automatic linking of speech input, each of said plurality of storage areas being associated with a corresponding one of said plurality of applications.

The present invention relates to a device designed to facilitate the management of voice data. Voice messages, left on a recipient's answerphone or delivered via a voicemail system are a popular form of person-to-person communication. Such voice messages are quick to generate for the sender but are relatively difficult to review for the recipient; speech is slow to listen to and, unlike inherently visual forms of messages such as electronic mail or handwritten notes, cannot be quickly scanned for the relevant information. The present invention aims to make it easier for users to extract relevant information from voice messages, and other kinds of voice record, such as recordings of meetings and recorded dictation.

In the long-term it would be desirable to approach this problem by automatically translating speech into text using speech recognition. Unfortunately this approach is not yet practical, since current speech recognition technology cannot accurately transcribe naturally-occurring speech of the kind found in voice messages. Therefore a number of approaches have been developed which help users to review voice data without actually recognising the speech signal and which provide for the display, structuring and annotation of speech recordings.

Many approaches assume, but do not necessarily depend on, an underlying technique for displaying a visual representation of speech. One such form of display is a single graphical line, graduated with time markings from start to finish (for example, a 4 second message may contain the appropriately spaced labels "0 sec", "1 sec", "2 sec", "3 sec", "4 sec"). In addition, an algorithm can be used to process the speech record to distinguish the major portions of speech from the major portions of silence. Such an algorithm is described by Arons (1994, Chapter 4). This permits a richer form of graphical display, in which the speech record is still portrayed along a timeline, but with portions of speech displayed as dark segments (for example) and the detected portions of silence displayed as light segments. Four pieces of prior art will be referred to:

1. A paper in the proceedings of CHI '92 entitled "Working with Audio: Integrating Personal Tape Recorders and Desktop Computers" by Degen, Mander and Saloman (1992) describes a prototype hand-held personal tape recorder. This is similar to a conventional "dictaphone" except that the user can place index points on the recording by pressing a button at the appropriate point in the recording. Two index buttons are available and these have no predetermined meaning. The user is free to place their own interpretation on the two forms of index. The recording can be downloaded to a personal computer and the inserted index points can be displayed along the timeline of the message. By visually displaying the index points, the user is reminded of an area of interest in the speech recording and can selectively play back portions of speech by using a pointing device such as a mouse. In addition, the index points can be searched for within the recording.

2. The NoteTaker product from InkWare Development Corp. (1994) extends this idea in the context of computer-based handwritten notes, rather than speech. Here users can select one of a variety of visual labels, representing for example "Urgent|", "Call" or "Action", and associate these with selected parts of a handwritten note. The program then allows the user to find all notes containing a particular label, an "Action" item for example.

3. Ades and Swinehart (1986) have built a prototype system for annotating and editing speech records. This system is the subject of their paper entitled "Voice Annotation and Editing in a Workstation Environment" from Xerox Corporation. In particular, an arbitrary text annotation can be placed on a visually displayed segment of speech as a cue to the content of that portion of speech.

4. A paper entitled "Capturing, Structuring and Representing Ubiquitous Audio" by Hindus, Schmandt and Horner (ACM Transactions on Information Systems, Vol 11, No.4 October 1993, pages 376-400) describes a prototype system for handling speech which allows the user to select a portion of visually displayed speech and to associate the depicted speech portion (such as by "drag-and-drop" using a mouse) with another application, such as a calendar. The calendar may contain independently entered, standard textual data (such as "Meeting with Jim"), as well as audio annotations and additions associated in this way.

Referring to the prior art items numbered 1-4 above, approaches (1)-(3) offer annotations which the user can employ as a visual cue to relevant parts of the speech (or handwriting, in the case of (2)). In (1), two labels are available with no predefined meaning. In (2), the user can choose from a broader set of labels, the appearance of which suggests a particular use (eg. the user should use the "Call" label for tagging items about telephoning people). In (3), the user can tag speech with an arbitrary textual entry, thus providing an even richer form of annotation. However, in all these approaches the label plays only a passive role in organising the target data. It is a passive visual and searchable cue to parts of the speech, and does not help the broader integration of the speech with other relevant applications in the user's personal information environment.

Approach (4) addresses this problem by allowing users to associate selected speech clips into, for example, a text-based calendar. A disadvantage of this approach is that it is rather laborious--the user must identify the appropriate speech clip, select it, and then associate it with another application. In addition, not all user interfaces lend themselves to this approach.

According to the present invention we provide a device for storing speech input comprising:

means for specifying a marker having a particular connotation;

means for associating the marker with all or part of the speech input;

and means for automatically linking the speech input associated with the marker to a corresponding storage area for later retrieval by the user in the context of a user interface which is dependent on the connotation of the associated marker.

A device according to the present invention has the advantage of providing a simple and convenient way of integrating voice data with other user applications so as to facilitate the management of voice data. In the embodiment to be described, the corresponding storage areas include telephone book and calendar application storage areas.

Preferably, the means for specifying a marker comprises means for selecting a marker from a set of markers. The set of markers preferably comprise iconic representations of the corresponding storage areas.

In the embodiment to be described there are means for displaying a representation of the speech input. This allows a user to view a visual representation of voice data on a desktop computer display. In that embodiment, there are means for automatically segmenting the speech input, specifically for automatically segmenting the speech input into silent and nonsilent parts.

The marker may be associated with a part of the speech input by time synchronisation. This approach conflates the selection of a marker and its association with a segment of speech data in a manner which may be particularly convenient for users. Alternatively, the marker may be associated with a part of the speech input by user input. The user input may comprise manipulation of an input device eg. dragging and dropping a marker icon on the relevant speech segment using a mouse. Alternatively, the user input may comprise means for associating a marker with a part of the speech input by spoken commands.

The linking means may comprise means for copying the speech input associated with the marker to the corresponding storage area. Alternatively, the linking means may comprise means for moving the speech input associated with the marker to the corresponding storage area. Another possibility is for the linking means to comprise means for providing a pointer to the speech input associated with the marker in the corresponding storage area. It may also be useful for the linking means to comprise means for providing an index into the original voice data containing the speech input associated with the marker.

Particular embodiments of the present invention will now be described, by way of example, with reference to the accompanying drawings of which:

FIG. 1. depicts the user interface of a device according to a first embodiment of the present invention;

FIG. 2. depicts the user interface of FIG. 1 after labelling of two speech segments;

FIG. 3. depicts the user interface of a known telephone book application.

The present invention can be implemented in the context of a "Personal Message Manager" application for browsing voice messages.

The embodiment to be described with reference to FIGS. 1 to 3 is written in Microsoft Visual Basic and Borland C on a IBM-compatible 486 25 MHz Personal Computer, and runs under the Microsoft Windows 3.1 operating system. Audio recording and playback facilities are supported by a SoundBlaster 16ASP card (Creative Labs, Inc.). These facilities are accessed through the standard MS Windows MultiMedia Application Programmers' Interface. Speech records are created using a microphone connected to the audio card, and played back via a set of speakers also connected to the card. On recording, the audio card translates the analogue audio signal produced by the microphone into a standard digital representation of the recorded speech, and stores the data in the standard ".wav" file format. The card performs the converse digital-to-analogue conversion in order to play back a digital ".wav" file through loudspeakers.

User input is by means of a mouse.

FIG. 1 shows an interaction screen 10 in a Microsoft Windows user interface. A set of folders represented by icons 12 are for storing previous voice messages. One of the folders 14 has been selected which causes the "header" information for each message in the selected folder to be displayed in a display box 16. The display box 16 displays the date of receipt and the sender of each message. FIG. 1 shows the topmost message 18 having been selected. This causes the selected message 18 to be displayed as a series of blocks in another display box 20. In the display box 20, dark blocks represent speech and white blocks represent silence. A known speech processing algorithm is utilised to distinguish between the major segments of speech and silence; such an algorithm is described in the paper by Arons (1994, Chapter 4).

Above the display box 20 is a set of audio controls 22 to allow the user to play, pause and stop speech playback. The audio controls 22 comprise the following button representations:

a play button 24;

a pause button 26;

a stop button 28;

a previous button 30 to skip playback to the previous segment of speech;

a next button 32 to skip playback to the next segment of speech;

a repeat button 34 to repeat playback of the most recently played segment of speech;

a speed control button 36 to vary the playback speed.

The user can also click directly on a segment of speech in the display box 20 eg using a mouse, to play back that specific segment. In FIG. 1, an arrow-shaped cursor 38 is shown in the display box 20 to indicate that playback is ready to commence at the beginning of the speech file. As a speech segment is being played, its colour changes to give the user a cue to the current position in the speech record.

To the right of the display box 20 is a panel 40 of markers 42,44,46,and 48 for labelling portions of the recorded speech. These can be used to provide a visual cue to the contents of a message. There are markers corresponding to a Phone Book 42, a Time/Appointment diary 44, a Memo/Reminder list 46, and a miscellaneous Points of Interest area 48. For example, one segment of the message 18 may contain a speech segment such as "If you need to get back to me, my number is 228 455." This segment could be labelled with the Phone marker 42. Whenever a marker is placed on a speech segment in the display box 20, that segment of speech is automatically linked to a corresponding application in the user's computer system. This automatic linking of speech segments to other applications using visual markers is convenient for the user and is an important step towards integrating the various applications relevant to handling voice data.

FIG. 2. depicts a situation in which the user has labelled two segments of speech, 50 and 52, the segment 50 as a Memo, and the segment 52 as a Phone item. This is accomplished by clicking the appropriate marker during playback of the relevant speech segment; the system then associates an instance of this marker with the segment of speech being played and provides a visual representation of the marker above the segment in the display box 20 as shown.

As well as providing a visual cue to the content of the speech record, placing markers against speech segments in the display box 20 automatically links the labelled segments to an appropriate computer application. For example, marking the message with the Phone label 42 as shown in FIG. 2. causes the marked segment of speech to be automatically added to a standard, textual Phone Book application, depicted in FIG. 3. The `Phone Book` window comprises a display box 54 listing the entries in the directory and two buttons, and `Add` button 56 and a `Delete` button 58 for use when adding and deleting entries in the list.

Items in the display box 54 which have voice data associated with them are indicated explicitly eg item 60 in FIG. 3. Selecting such an item in the display box 54 causes the appropriate speech clip to be played back.

An advantage of the approach described above is that it provides a very quick and easy method of capturing and storing information, whilst it is listened to in spoken form. Later, at a time more convenient to the user, he/she can transcribe this portion of speech into a full textual phone book entry if desired.

In order to associate the selected marker with a specific segment of speech, it is necessary to determine the segment of speech that is currently being played. There are a number of ways in which this can be implemented and one method is described here. Assume the algorithm used for speech/silence detection (such as Arons, 1994) has produced a data file indicating the times in the speech file of speech and silence.

For example:

Speech (1): 0 millisecond (ms) to 800 ms

Silence: 801 ms to 1050 ms

Speech (2): 1051 ms to 3405 ms

Silence: 3406 ms to 3920 ms

Speech (3): 3921 ms to 6246 ms

Suppose the speech message is played back from the start of the message. At the start of the playback, an internal clock is set to 0ms to track the time. If the user selects (ie. clicks) a marker, the time is noted say, 5324 ms, and then the speech/silence data file, illustrated above, is searched to see to which segment this time corresponds. In the above example this implies that the system is currently playing the third speech segment. In this way, time-synchronization is used to associate a marker with a speech segment.

In order automatically to link to another application and subsequently to play a speech clip from that application, a visual indication of the speech within that application is provided and the relevant application must be able to play back the speech clip directly. This is accomplished using standard MS Windows programming techniques. In the Phone Book example, an automatically generated textual entry is added to the Phone Book display (for example, see item 60 in FIG. 3). In addition, in the underlying data structure, this entry is flagged as being voice data and a simple specification of where to find the appropriate voice data is recorded. This specification comprises a pointer to the original ".wav" speech file, along with a specification of start and end points within this file that represent the speech segment to be accessed. These points can be specified as times, byte positions, or other representations. When selected, the audio Application Programmers' Interface is used to play back this segment of speech from within the Phone Book application.

The embodiment described above is a voice data management device which is easy to use and which integrates voice data into other user applications in a convenient manner. Many of the features described with reference to this embodiment can be modified and categories of these will now be addressed.

1. Selection of Speech Marker

Apart from a mouse, other possible selection devices include a pen/stylus, a touch-screen and the use of the TAB key on a keyboard for iteratively cycling through menu selection options displayed to the user. Alternatively, each marker could be represented by a dedicated hard button on a device implementing the present invention and pressed during playback of recorded speech.

2. Association of Markers with Speech

In the embodiment described above, the timing of the marker selection governs the speech segment with which it is to be associated. An alternative is to allow the user actively to associate a marker with the speech segment of interest eg by "drag-and-drop". This approach is particularly useful after the message has been listened to at least once when the user is undertaking considered analysis and structuring of the speech file.

An alternative set of approaches conflate the selection and association steps. The user may select the speech segment of interest, either by explicit selection with a mouse, or implicit selection by time synchronisation, and linguistically specify the marker to be associated with that segment. The linguistic specification could be made by typing in some initial identifying characters of the name of the marker (eg. "ph" for Phone), by drawing or hand-writing the name of the marker and using handwriting recognition to determine the intended marker, or by speaking the name of the marker and using speech recognition to identify it.

A final general approach to marker association is automatically to identify the appropriate marker for a segment of speech by partially recognising the speech itself. Here techniques for "word-spotting" in continuous speech, for example based on Hidden Markov Models (cf. Wilcox and Bush, 1991), could determine the likelihood that a certain speech segment contains a telephone number. If the recognition algorithm predicts a high probablility of a phone number, the segment could be labelled automatically with the Phone marker.

3. Definition of Markers

It is anticipated that the user may be able to customise the markers and corresponding storage areas available within a system according to the present invention. A suite of icons could be made available from which the user can choose. In addition, the user could define arbitrary text labels and place these in the panel of markers. The system could also allow the user to specify the storage area associated with each marker.

4. Accessing Speech Segments from Target Application

The above description assumes that the storage application (eg. Phone Book) is provided with a link to the original speech file. There are various ways in which this could be implemented:

i) Copy--a copy of the appropriate speech data could be made and stored in a separate file;

ii) Move--a copy of the appropriate speech data could be made and stored in a separate file, and the segment could be removed from the original voice record (ie. from the voice message);

iii) Link--as in the above-described embodiment, a pointer to the same speech file can be provided.

Another approach is to treat the copied/linked speech clip as representing an index into the original message. In this case, when the clip is played back from the application (eg. the Phone Book), the user has the option of reviewing the entire message from which it was extracted. This is a useful enhancement since an automatic segmentation algorithm will sometimes produce inappropriate segmentations, for example breaking a telephone number in the middle, in which case it is important for the user to be able to continue playback (or rewind) after the linked speech clip has been played.

5. Extracting Segments from the Original Speech Record

In the above-described embodiment, the speech record is segmented into speech and silence using an algorithm such as Arons (1994, Chapter 4). Alternatively, the original speech record could be represented to the user as a continous, unstructured line. Markers could be associated with this line using the same range of techniques described above and the only difference would be that the marker is associated with a point in the speech record rather than a segment of speech.

Automatically storing the speech associated with a marker could then be accomplished by either (a) arbitrarily defining the segment of interest eg. a 5 second clip centred on the marker point, or (b) assuming the indexing approach outlined in point (4) above, where the storage of the speech in the target application is merely a point at which to index into the original.

6. User Interface Designs

Whenever a marker is associated with a segment of speech, an instance of that marker could appear in the "header" line for the message (along with date, sender, etc). This would provide a cue to the user that the message contains eg. a phone number. A possible additional feature would be to play back every segment in the relevant message which has been associated with this type of marker on selection of the header marker by the user eg by clicking with the mouse.

Moreover, a "find" facility could be included with the Personal Message Manager which could find all messages containing a certain type of marker, or combination of marker.

7. Device without a Display

The present invention also has application in a device which lacks a display. Such a device may be useful for visually impaired people, for whom speech-based information is more useful than visual information. Speech messages could be reviewed using a set of hard buttons, similar to those used in dictaphones for example, and interesting portions of speech could be labelled using a set of hard marker buttons (as described in (1) above). Such portions could then be linked as described above to speech-based storage areas, such as a speech-based phone book.

The present invention is relevant to a range of uses of speech data. It may have particular utility for users who receive a large amount of voice mail containing similar kinds of information. This information may not need to be transcribed immediately, but it may help to store the spoken information in a structured form. For example, field staff may telephone a central office to report the time of a repair, the problem diagnosed and the work undertaken. This information could be extracted from the voice messages and categorised using the techniques described.

The invention has been described in terms of a program for handling voice messages. However, the invention is applicable to all forms of recorded speech, and the implementation described need not necessarily be part of a telecommunications system. Other possible uses include the management of voice data comprising recording of meetings, general conversations and other personal data.

Haddock, Nicholas John

Patent Priority Assignee Title
10049663, Jun 08 2016 Apple Inc Intelligent automated assistant for media exploration
10049668, Dec 02 2015 Apple Inc Applying neural network language models to weighted finite state transducers for automatic speech recognition
10049675, Feb 25 2010 Apple Inc. User profiling for voice input processing
10057736, Jun 03 2011 Apple Inc Active transport based notifications
10067938, Jun 10 2016 Apple Inc Multilingual word prediction
10074360, Sep 30 2014 Apple Inc. Providing an indication of the suitability of speech recognition
10078631, May 30 2014 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
10079014, Jun 08 2012 Apple Inc. Name recognition system
10083688, May 27 2015 Apple Inc Device voice control for selecting a displayed affordance
10083690, May 30 2014 Apple Inc. Better resolution when referencing to concepts
10089072, Jun 11 2016 Apple Inc Intelligent device arbitration and control
10101822, Jun 05 2015 Apple Inc. Language input correction
10102359, Mar 21 2011 Apple Inc. Device access using voice authentication
10108612, Jul 31 2008 Apple Inc. Mobile device having human language translation capability with positional feedback
10127220, Jun 04 2015 Apple Inc Language identification from short strings
10127911, Sep 30 2014 Apple Inc. Speaker identification and unsupervised speaker adaptation techniques
10134385, Mar 02 2012 Apple Inc.; Apple Inc Systems and methods for name pronunciation
10169329, May 30 2014 Apple Inc. Exemplar-based natural language processing
10170123, May 30 2014 Apple Inc Intelligent assistant for home automation
10176167, Jun 09 2013 Apple Inc System and method for inferring user intent from speech inputs
10185542, Jun 09 2013 Apple Inc Device, method, and graphical user interface for enabling conversation persistence across two or more instances of a digital assistant
10186254, Jun 07 2015 Apple Inc Context-based endpoint detection
10192552, Jun 10 2016 Apple Inc Digital assistant providing whispered speech
10199051, Feb 07 2013 Apple Inc Voice trigger for a digital assistant
10223066, Dec 23 2015 Apple Inc Proactive assistance based on dialog communication between devices
10241644, Jun 03 2011 Apple Inc Actionable reminder entries
10241752, Sep 30 2011 Apple Inc Interface for a virtual digital assistant
10249300, Jun 06 2016 Apple Inc Intelligent list reading
10255907, Jun 07 2015 Apple Inc. Automatic accent detection using acoustic models
10269345, Jun 11 2016 Apple Inc Intelligent task discovery
10276170, Jan 18 2010 Apple Inc. Intelligent automated assistant
10283110, Jul 02 2009 Apple Inc. Methods and apparatuses for automatic speech recognition
10289433, May 30 2014 Apple Inc Domain specific language for encoding assistant dialog
10297253, Jun 11 2016 Apple Inc Application integration with a digital assistant
10311871, Mar 08 2015 Apple Inc. Competing devices responding to voice triggers
10318871, Sep 08 2005 Apple Inc. Method and apparatus for building an intelligent automated assistant
10354011, Jun 09 2016 Apple Inc Intelligent automated assistant in a home environment
10366158, Sep 29 2015 Apple Inc Efficient word encoding for recurrent neural network language models
10381016, Jan 03 2008 Apple Inc. Methods and apparatus for altering audio output signals
10431204, Sep 11 2014 Apple Inc. Method and apparatus for discovering trending terms in speech requests
10446141, Aug 28 2014 Apple Inc. Automatic speech recognition based on user feedback
10446143, Mar 14 2016 Apple Inc Identification of voice inputs providing credentials
10475446, Jun 05 2009 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
10490187, Jun 10 2016 Apple Inc Digital assistant providing automated status report
10496753, Jan 18 2010 Apple Inc.; Apple Inc Automatically adapting user interfaces for hands-free interaction
10497365, May 30 2014 Apple Inc. Multi-command single utterance input method
10509862, Jun 10 2016 Apple Inc Dynamic phrase expansion of language input
10521466, Jun 11 2016 Apple Inc Data driven natural language event detection and classification
10552013, Dec 02 2014 Apple Inc. Data detection
10553209, Jan 18 2010 Apple Inc. Systems and methods for hands-free notification summaries
10567477, Mar 08 2015 Apple Inc Virtual assistant continuity
10568032, Apr 03 2007 Apple Inc. Method and system for operating a multi-function portable electronic device using voice-activation
10592095, May 23 2014 Apple Inc. Instantaneous speaking of content on touch devices
10593346, Dec 22 2016 Apple Inc Rank-reduced token representation for automatic speech recognition
10607140, Jan 25 2010 NEWVALUEXCHANGE LTD. Apparatuses, methods and systems for a digital conversation management platform
10607141, Jan 25 2010 NEWVALUEXCHANGE LTD. Apparatuses, methods and systems for a digital conversation management platform
10657961, Jun 08 2013 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
10659851, Jun 30 2014 Apple Inc. Real-time digital assistant knowledge updates
10671428, Sep 08 2015 Apple Inc Distributed personal assistant
10679605, Jan 18 2010 Apple Inc Hands-free list-reading by intelligent automated assistant
10691473, Nov 06 2015 Apple Inc Intelligent automated assistant in a messaging environment
10705794, Jan 18 2010 Apple Inc Automatically adapting user interfaces for hands-free interaction
10706373, Jun 03 2011 Apple Inc. Performing actions associated with task items that represent tasks to perform
10706841, Jan 18 2010 Apple Inc. Task flow identification based on user intent
10733993, Jun 10 2016 Apple Inc. Intelligent digital assistant in a multi-tasking environment
10747498, Sep 08 2015 Apple Inc Zero latency digital assistant
10762293, Dec 22 2010 Apple Inc.; Apple Inc Using parts-of-speech tagging and named entity recognition for spelling correction
10789041, Sep 12 2014 Apple Inc. Dynamic thresholds for always listening speech trigger
10791176, May 12 2017 Apple Inc Synchronization and task delegation of a digital assistant
10791216, Aug 06 2013 Apple Inc Auto-activating smart responses based on activities from remote devices
10795541, Jun 03 2011 Apple Inc. Intelligent organization of tasks items
10810274, May 15 2017 Apple Inc Optimizing dialogue policy decisions for digital assistants using implicit feedback
10904611, Jun 30 2014 Apple Inc. Intelligent automated assistant for TV user interactions
10978090, Feb 07 2013 Apple Inc. Voice trigger for a digital assistant
10984326, Jan 25 2010 NEWVALUEXCHANGE LTD. Apparatuses, methods and systems for a digital conversation management platform
10984327, Jan 25 2010 NEW VALUEXCHANGE LTD. Apparatuses, methods and systems for a digital conversation management platform
11010550, Sep 29 2015 Apple Inc Unified language modeling framework for word prediction, auto-completion and auto-correction
11025565, Jun 07 2015 Apple Inc Personalized prediction of responses for instant messaging
11037565, Jun 10 2016 Apple Inc. Intelligent digital assistant in a multi-tasking environment
11069347, Jun 08 2016 Apple Inc. Intelligent automated assistant for media exploration
11080012, Jun 05 2009 Apple Inc. Interface for a virtual digital assistant
11087759, Mar 08 2015 Apple Inc. Virtual assistant activation
11120372, Jun 03 2011 Apple Inc. Performing actions associated with task items that represent tasks to perform
11133008, May 30 2014 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
11152002, Jun 11 2016 Apple Inc. Application integration with a digital assistant
11257504, May 30 2014 Apple Inc. Intelligent assistant for home automation
11405466, May 12 2017 Apple Inc. Synchronization and task delegation of a digital assistant
11410053, Jan 25 2010 NEWVALUEXCHANGE LTD. Apparatuses, methods and systems for a digital conversation management platform
11423886, Jan 18 2010 Apple Inc. Task flow identification based on user intent
11500672, Sep 08 2015 Apple Inc. Distributed personal assistant
11526368, Nov 06 2015 Apple Inc. Intelligent automated assistant in a messaging environment
11556230, Dec 02 2014 Apple Inc. Data detection
11587559, Sep 30 2015 Apple Inc Intelligent device identification
6055495, Jun 07 1996 HEWLETT-PACKARD DEVELOPMENT COMPANY, L P Speech segmentation
6453281, Jul 30 1996 CONPACT, INC Portable audio database device with icon-based graphical user-interface
6571211, Nov 21 1997 Nuance Communications, Inc Voice file header data in portable digital audio recorder
6671567, Nov 21 1997 Nuance Communications, Inc Voice file management in portable digital audio recorder
6859526, Jul 03 2001 Hewlett Packard Enterprise Development LP System and program product for managing call information
6912691, Sep 03 1999 Cisco Technology, Inc Delivering voice portal services using an XML voice-enabled web server
6961700, Sep 24 1996 ALLVOICE DEVELOPMENTS US, LLC Method and apparatus for processing the output of a speech recognition engine
7017161, Oct 11 1999 Nuance Communications, Inc System and method for interfacing a radiology information system to a central dictation system
7035807, Feb 19 2002 Sound on sound-annotations
7203288, Nov 21 1997 Nuance Communications, Inc Intelligent routing of voice files in voice data management system
7284049, Jan 28 2002 CREDIT SUISSE AS ADMINISTRATIVE AGENT Selective dedication of active and passive contact center recording resources
7369649, Aug 15 2003 AVAYA LLC System and method for caller initiated voicemail annotation and its transmission over IP/SIP for flexible and efficient voice mail retrieval
7376735, Jan 31 2002 CREDIT SUISSE AS ADMINISTRATIVE AGENT Method, apparatus, and system for capturing data exchanged between a server and a user
7424715, Jan 28 2002 VERINT AMERICAS INC Method and system for presenting events associated with recorded data exchanged between a server and a user
7424718, Jan 28 2002 CREDIT SUISSE AS ADMINISTRATIVE AGENT Method and system for presenting events associated with recorded data exchanged between a server and a user
7453991, Dec 08 1999 Nuance Communications, Inc Method and apparatus for voice mail notes
7653872, Jun 30 2004 FUJIFILM Business Innovation Corp Document processor, document processing method and storage medium storing document processing program
7664235, Dec 08 1999 Nuance Communications, Inc Method and apparatus for voice mail notes
7746730, Sep 05 2007 Multifunction reminder system
7882212, Jan 28 2002 VERINT AMERICAS INC Methods and devices for archiving recorded interactions and retrieving stored recorded interactions
7953719, Jan 31 2002 Verint Systems Inc. Method, apparatus, and system for capturing data exchanged between a server and a user
7995711, Dec 08 1999 Nuance Communications, Inc Method and apparatus for voice mail notes
7995745, Aug 11 2006 Structure and method for echo reduction without loss of information
8030563, Jan 16 2009 Hon Hai Precision Industry Co., Ltd. Electronic audio playing apparatus and method
8077839, Jan 09 2007 SHENZHEN XINGUODU TECHNOLOGY CO , LTD Handheld device for dialing of phone numbers extracted from a voicemail
8204186, Feb 13 2001 Daedalus Blue LLC Selectable audio and mixed background sound for voice messaging system
8300776, Jul 15 2009 GOOGLE LLC Highlighting of voice message transcripts
8351581, Dec 19 2008 RAKUTEN GROUP, INC Systems and methods for intelligent call transcription
8391844, Jan 07 2007 Apple Inc Voicemail systems and methods
8417223, Aug 24 2010 GOOGLE LLC Advanced voicemail features without carrier voicemail support
8422663, Aug 11 2006 Structure and method for echo reduction without loss of information
8498625, Aug 24 2010 GOOGLE LLC Advanced voicemail features without carrier voicemail support
8499024, Sep 03 1999 Cisco Technology, Inc. Delivering voice portal services using an XML voice-enabled web server
8509398, Apr 02 2009 Microsoft Technology Licensing, LLC Voice scratchpad
8553856, Jan 07 2007 Apple Inc Voicemail systems and methods
8588378, Jul 15 2009 GOOGLE LLC Highlighting of voice message transcripts
8611507, Dec 19 2008 RAKUTEN GROUP, INC Systems and methods for intelligent call transcription
8654939, Feb 13 2001 International Business Machines Corporation Recording and receiving voice mail with freeform bookmarks
8892446, Jan 18 2010 Apple Inc. Service orchestration for intelligent automated assistant
8903716, Jan 18 2010 Apple Inc. Personalized vocabulary for digital assistant
8909199, Jan 07 2007 Apple Inc. Voicemail systems and methods
8930191, Jan 18 2010 Apple Inc Paraphrasing of user requests and results by automated digital assistant
8942986, Jan 18 2010 Apple Inc. Determining user intent based on ontologies of domains
9008300, Feb 24 2006 VERINT AMERICAS INC Complex recording trigger
9117447, Jan 18 2010 Apple Inc. Using event alert text as input to an automated assistant
9262612, Mar 21 2011 Apple Inc.; Apple Inc Device access using voice authentication
9300784, Jun 13 2013 Apple Inc System and method for emergency calls initiated by voice command
9318108, Jan 18 2010 Apple Inc.; Apple Inc Intelligent automated assistant
9325854, Aug 11 2006 Structure and method for echo reduction without loss of information
9330720, Jan 03 2008 Apple Inc. Methods and apparatus for altering audio output signals
9338493, Jun 30 2014 Apple Inc Intelligent automated assistant for TV user interactions
9368114, Mar 14 2013 Apple Inc. Context-sensitive handling of interruptions
9430463, May 30 2014 Apple Inc Exemplar-based natural language processing
9451086, Feb 24 2006 Verint Americas Inc. Complex recording trigger
9483461, Mar 06 2012 Apple Inc.; Apple Inc Handling speech synthesis of content for multiple languages
9495129, Jun 29 2012 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
9502031, May 27 2014 Apple Inc.; Apple Inc Method for supporting dynamic grammars in WFST-based ASR
9535906, Jul 31 2008 Apple Inc. Mobile device having human language translation capability with positional feedback
9548050, Jan 18 2010 Apple Inc. Intelligent automated assistant
9576574, Sep 10 2012 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
9582608, Jun 07 2013 Apple Inc Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
9620104, Jun 07 2013 Apple Inc System and method for user-specified pronunciation of words for speech synthesis and recognition
9620105, May 15 2014 Apple Inc. Analyzing audio input for efficient speech and music recognition
9626955, Apr 05 2008 Apple Inc. Intelligent text-to-speech conversion
9633004, May 30 2014 Apple Inc.; Apple Inc Better resolution when referencing to concepts
9633660, Feb 25 2010 Apple Inc. User profiling for voice input processing
9633674, Jun 07 2013 Apple Inc.; Apple Inc System and method for detecting errors in interactions with a voice-based digital assistant
9646609, Sep 30 2014 Apple Inc. Caching apparatus for serving phonetic pronunciations
9646614, Mar 16 2000 Apple Inc. Fast, language-independent method for user authentication by voice
9668024, Jun 30 2014 Apple Inc. Intelligent automated assistant for TV user interactions
9668121, Sep 30 2014 Apple Inc. Social reminders
9697820, Sep 24 2015 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
9697822, Mar 15 2013 Apple Inc. System and method for updating an adaptive speech recognition model
9711141, Dec 09 2014 Apple Inc. Disambiguating heteronyms in speech synthesis
9715875, May 30 2014 Apple Inc Reducing the need for manual start/end-pointing and trigger phrases
9721566, Mar 08 2015 Apple Inc Competing devices responding to voice triggers
9734193, May 30 2014 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
9760559, May 30 2014 Apple Inc Predictive text input
9785630, May 30 2014 Apple Inc. Text prediction using combined word N-gram and unigram language models
9798393, Aug 29 2011 Apple Inc. Text correction processing
9818400, Sep 11 2014 Apple Inc.; Apple Inc Method and apparatus for discovering trending terms in speech requests
9842101, May 30 2014 Apple Inc Predictive conversion of language input
9842105, Apr 16 2015 Apple Inc Parsimonious continuous-space phrase representations for natural language processing
9858925, Jun 05 2009 Apple Inc Using context information to facilitate processing of commands in a virtual assistant
9865248, Apr 05 2008 Apple Inc. Intelligent text-to-speech conversion
9865280, Mar 06 2015 Apple Inc Structured dictation using intelligent automated assistants
9886432, Sep 30 2014 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
9886953, Mar 08 2015 Apple Inc Virtual assistant activation
9899019, Mar 18 2015 Apple Inc Systems and methods for structured stem and suffix language models
9922642, Mar 15 2013 Apple Inc. Training an at least partial voice command system
9934775, May 26 2016 Apple Inc Unit-selection text-to-speech synthesis based on predicted concatenation parameters
9953088, May 14 2012 Apple Inc. Crowd sourcing information to fulfill user requests
9959870, Dec 11 2008 Apple Inc Speech recognition involving a mobile device
9966060, Jun 07 2013 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
9966065, May 30 2014 Apple Inc. Multi-command single utterance input method
9966068, Jun 08 2013 Apple Inc Interpreting and acting upon commands that involve sharing information with remote devices
9971774, Sep 19 2012 Apple Inc. Voice-based media searching
9972304, Jun 03 2016 Apple Inc Privacy preserving distributed evaluation framework for embedded personalized systems
9986419, Sep 30 2014 Apple Inc. Social reminders
Patent Priority Assignee Title
5481645, May 14 1992 Ing. C. Olivetti & C., S.p.A. Portable computer with verbal annotations
5526407, Sep 30 1991 Riverrun Technology Method and apparatus for managing information
WO9202009,
WO9211634,
//////////
Executed onAssignorAssigneeConveyanceFrameReelDoc
Apr 19 1995Hewlett-Packard Company(assignment on the face of the patent)
Apr 21 1995Hewlett-Packard LimitedHewlett-Packard CompanyASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0088260152 pdf
May 20 1998Hewlett-Packard CompanyHewlett-Packard CompanyMERGER SEE DOCUMENT FOR DETAILS 0115230469 pdf
Jan 31 2003Hewlett-Packard CompanyHEWLETT-PACKARD DEVELOPMENT COMPANY, L P ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0269450699 pdf
Apr 30 2013HEWLETT-PACKARD DEVELOPMENT COMPANY, L P Palm, IncASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0303410459 pdf
Dec 18 2013HEWLETT-PACKARD DEVELOPMENT COMPANY, L P Palm, IncASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0318370544 pdf
Dec 18 2013Palm, IncHEWLETT-PACKARD DEVELOPMENT COMPANY, L P ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0318370239 pdf
Jan 23 2014Hewlett-Packard CompanyQualcomm IncorporatedASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0321320001 pdf
Jan 23 2014Palm, IncQualcomm IncorporatedASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0321320001 pdf
Jan 23 2014HEWLETT-PACKARD DEVELOPMENT COMPANY, L P Qualcomm IncorporatedASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS 0321320001 pdf
Date Maintenance Fee Events
Jun 22 2001ASPN: Payor Number Assigned.
Sep 28 2001M183: Payment of Maintenance Fee, 4th Year, Large Entity.
Oct 21 2005M1552: Payment of Maintenance Fee, 8th Year, Large Entity.
Oct 21 2009M1553: Payment of Maintenance Fee, 12th Year, Large Entity.


Date Maintenance Schedule
Apr 21 20014 years fee payment window open
Oct 21 20016 months grace period start (w surcharge)
Apr 21 2002patent expiry (for year 4)
Apr 21 20042 years to revive unintentionally abandoned end. (for year 4)
Apr 21 20058 years fee payment window open
Oct 21 20056 months grace period start (w surcharge)
Apr 21 2006patent expiry (for year 8)
Apr 21 20082 years to revive unintentionally abandoned end. (for year 8)
Apr 21 200912 years fee payment window open
Oct 21 20096 months grace period start (w surcharge)
Apr 21 2010patent expiry (for year 12)
Apr 21 20122 years to revive unintentionally abandoned end. (for year 12)